CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6109-6117
DOI: 10.1609/aaai.v40i8.37535 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hao Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).
Abstract (Originalsprache)
RGB-Thermal (RGBT) tracking aims to exploit visible and thermal infrared modalities for robust all-weather object tracking. However, existing RGBT trackers struggle to resolve modality discrepancies, which poses great challenges for robust feature representation. This limitation hinders effective cross-modal information propagation and fusion, which significantly reduces the tracking accuracy. To address this limitation, we propose a novel Contextual Aggregation with Deformable Alignment framework called CADTrack for RGBT Tracking. To be specific, we first deploy the Mamba-based Feature Interaction (MFI) that establishes efficient feature interaction via state space models. This interaction module can operate with linear complexity, reducing computational cost and improving feature discrimination. Then, we propose the Contextual Aggregation Module (CAM) that dynamically activates backbone layers through sparse gating based on the Mixture-of-Experts (MoE). This module can encode complementary contextual information from cross-layer features. Finally, we propose the Deformable Alignment Module (DAM) to integrate deformable sampling and temporal propagation, mitigating spatial misalignment and localization drift. With the above components, our CADTrack achieves robust and accurate tracking in complex scenarios. Extensive experiments on five RGBT tracking benchmarks verify the effectiveness of our proposed method.
Zitieren
APA
Li, H., Wang, Y., Hu, X., Hao, W., Zhang, P., Wang, D., & Lu, H. (2026). CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6109-6117. https://doi.org/10.1609/aaai.v40i8.37535
Vancouver
Li H, Wang Y, Hu X, Hao W, Zhang P, Wang D, et al. CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6109-6117. doi:10.1609/aaai.v40i8.37535
BibTeX
@article{Li2026,
author = {Li, Hao and Wang, Yuhao and Hu, Xiantao and Hao, Wenning and Zhang, Pingping and Wang, Dong and Lu, Huchuan},
title = {CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6109--6117},
doi = {10.1609/aaai.v40i8.37535}
}
EUVIMED